Research on OpenCL optimization for FPGA deep learning application

Abstract

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance.

Deep Learning Optimization of Microgrid Economic Dispatch and Wireless Power Transmission Using Blockchain

“…Various encryption technologies are built into the blockchain to ensure data security and tamper-proof user privacy. This feature can effectively ensure the information security of distributed agents in the microgrid [14].…”

X-Ray Tomography Reconstruction Accelerated on FPGA Through High-Level Synthesis Tools

“…FPGAs based on HLS tools are experiencing great consideration as an acceleration platform for many applications such as high-performance computing [3]- [5] or deep neural networks [6], [7]. The maturity of the HLS tools, making them easier to use, and their many built-in floating-point units (e.g., Digital Signal Processing (DSP) units) in the latest FPGAs explain this interest.…”

OpenCL FPGA Optimization guided by memory accesses and roofline model analysis applied to tomography acceleration

“…Field programmable gate arrays (FPGAs) based on HLS tools are experiencing great consideration as an acceleration platform for many applications such as highperformance computing [1], [2], [3], deep neural networks [4], [5]. The maturity of their architectures and many built-in floating-point units (DSPs) in the latest FPGAs explain this interest.…”